Mechatronics for Safety, Security and Dependability in a New Era - Arai and Arai Part 9 ppt

224 Ch46-I044963.fm Page 224 Tuesday, August 1, 2006 3:57 PM Ch46-I044963.fm Page 224 Tuesday, August 1, 2006 3:57 PM 224 We use the SAD (Sum of Absolute Difference) algorithm for the area-based stereo matching in order to extract disparity image (Moon, et al. 2002). In this study, the walls of buildings are extracted from the regions with a same value in the disparity image. The Building regions are extracted using the height information from the disparity information with a priori knowledge of the one-floor height of building. Vanishing Points A non-vertical skyline caused by the roof of a building can provide information on the relative orientation between the robot and the building. What is necessary for estimating the relative orientation is the vanishing point. We first calculate the vanishing points of the non-vertical skylines with the horizontal scene axis. And we estimate an angle between the image plane and the line from the camera center to a vanishing point which is parallel to the direction of a visible wall in the building. Corners of Buildings The boundaiy lines are the vertical skylines of buildings adjoining to the sky regions (Katsura, et al. 2003). The boundary lines correspond to the corners of buildings on the given map. Figure 1: A boundary line and two vanishing points. Figure 1 shows an extraction result of a corner of building (CB) from a vertical skyline and two vanishing points (VP1 and VP2) from two non-vertical skylines, respectively. The vertical and non- vertical skylines are adjoining to the sky region at the top right of the image. ROUGH MAP Although an accurate map provides accurate and efficient localization, it needs a lot of cost to build and update (Tomono, et al. 2001). A solution to this problem would be to allow a map to be defined roughly since a rough map is much easier to build. The rough map is defined as a 2D segment-based map that contains approximate metric information about the poses and dimensions of buildings. It also has rough metric information about the distances and the relative directions between the buildings present in the environment. The map may carry a characteristic of the initial position as a current position and the goal position on the map. The approximate outlines of the buildings can be also represented in the map and thus used for recognizing the buildings in the environment during the navigation. And besides, we can arrange the route of robot on the map (Chronis, et al. 2003). Figure 2 shows a guide map for visitors to our university campus and an example of rough map. We use this map as a rough map representation for 225 Ch46-I044963.fm Page 225 Tuesday, August 1, 2006 3:57 PM Ch46-I044963.fm Page 225 Tuesday, August 1, 2006 3:57 PM 225 our localization experiments. We approximate the buildings on the map to the polygons and compute the uncertainties of their poses and dimensions for estimating the uncertainty of robot pose from the map matching. i1 "I u tf1 Tl l±z 12 S2[ M3 Zl 1 1 us / M in 4 ap. tsst " (a) (b ) Figure 2: A guide map of our university campus (a) and an example of rough map (b). LOCALIZATION The robot matches the extracted planar surfaces from the disparity image to the building walls on the map using the Mahalanobis distance criterion. Note that the distance is a quantity which is computed in the disparity space. The disparity space is constructed such that the x-y plane coincides with the image plane and the disparity axis d is perpendicular to the image plane. The map matching provides for a correction of the estimated pose of the robot that must be integrated with odometry information. We use an extended Kalman filter for the estimation of the robot pose from the result of the map matching and this integration (DeSouza, et al. 2002). Kalman Filter Framework Prediction The state prediction X(k+l|k) and its associated covariance 2x(k+l|k) is determined from odometry based on the previous state X(k|k) and 2x(k|k). The modeled features in the map, M, get transformed into the observation frame. The measurement prediction z(k+l) = H(X(k+\ |k), M), where H is the non- linear measurement model. Error Propagation is done by a first-order approximation which requires the Jacobian Jx of H with respect to the state prediction X(k+1 |k). Observation The parameters of features constitute the vector of observation Z(k+1). Their associated covariance estimates constitute the observation covariance matrix _R(k+l). Successfully matched observation and predictions yield the innovations (1) 226 Ch46-I044963.fm Page 226 Tuesday, August 1, 2006 3:57 PM Ch46-I044963.fm Page 226 Tuesday, August 1, 2006 3:57 PM 226 and their innovation covariance S(k+]) = J x E x (k+\ |k>/x T + #(k+l). (2) Update Finally, with the filter equations IV(k+l) = J7 x (k+l|k)./xV(k+l), (3 ) Jf(k+l|k+l) = Jf(k+l|k) + W(k+\)V(k+\\ (4) 2k(k+l|k+l) = 2x(k+l|k) - W{k+l)S(\<.+\)W 1 {k+\). (5) the posterior estimates of the robot pose and associated covariance are computed. Filter Setup for the Walls of Buildings We formulate the walls of buildings by y = A + Bx in the map and those transformed into the disparity space by y = a+fix with z = (a, J3) T . The observation equation Z = (a,J3) J of the walls of buildings in disparity image is described as follows: ' = F(X,L) + v fl Sm0p ~ A + Bx p -y p -I A + Bx p -y p + v, (6) where X= (x p , y p , 9 P ) T is the robot pose, L = (A, B) T the map parameter, and v the random observation error. The filter setup for this feature is as follows: I.v, (2) ' (3)' where Jx and JL are the respective Jacobians of F w.r.t. Xand L, and Ex, EL and E, are the uncertainty covariance matrices of X, L and v, respectively. Filter Setup from the Vanishing Points We can directly observe the robot orientation using the angle from vanishing point and the direction of building. Thus the observation Z = n/2 + Ob- 0 vp , where Of, is the direction angle of a wall of building and 0,-p, the angle from the vanishing point, and the prediction z = 0 r is the robot orientation of the last step. The filter setup for this feature is as follows: = [00 l]x A {0 0 I]'', (2)" (3)" 227 Ch46-I044963.fm Page 227 Tuesday, August 1, 2006 3:57 PM Ch46-I044963.fm Page 227 Tuesday, August 1, 2006 3:57 PM 227 Filter Setup for the Corners of Buildings After we found the corresponding corner of building to the boundary line Z = (x, d) T in the disparity space, the observation equation can be described like the following equation: = H(X,M) + v ' ( m x -x p )s'm0 p -(m y -y p )cos0 p (m x -x p )cos0 p +(m y -y p )sm0 p fl (m x - x p ) cos 6 p + (m y -y p )sin0 p + v, (7) where M = (m x , m v ) T is the coordinates of the building corner on the map. The filter setup for this feature is as follows: S = Jx^xJ T x + JMT.MJ T M M (2)' " (3)' " EXPERIMENTAL RESULTS The experimental results are shown in figure 3 magnified from figure 2 which shows the estimation of the robot pose by the localization algorithms using the EKF. The color ellipses with 1 cr uncertainty are the estimated uncertainties of the robot poses by matching the features to the map. T [m] 20 15 10 5 0 -5 -10 -15 -20 -25 Localizatio n Result s B2 :M3 1 -30 -25 -20 -15 -10 -5 X [m] 10 15 20 Figure 3: Localization results with uncertainty ellipses. Table 1 shows the estimates of the robot pose in each feature used by the localization algorithm. The left figures of each table row represent the estimate of the localization method. The right parenthesized figures of the same row represent the standard deviation of the robot pose. 228 Color Feature x (m) (std. dev.) y (m) (std. dev.) θ ( °) (std. dev.) green Odometry -5.0 (10.0) -10.0 (10.0) 140.0 (10.0) cyan Disparity -9.5 (7.5) -6.8 (5.6) 141.8 (7.5) magenta Vanishing Point 1 -9.0 (6.7) -6.3 (4.3) 142.7 (4.7) blue Vanishing Point 2 -7.8 (6.4) -5.0 (3.7) 144.8 (3.1) red Corner -4.7 (6.2) -10.5 (3.6) 148.8 (3.0) Ch46-I044963.fm Page 228 Tuesday, August 1, 2006 3:57 PM Ch46-I044963.fm Page 228 Tuesday, August 1, 2006 3:57 PM 228 TABLE 1 ROBOT POSE AND STANDARD DEVIATION BY EACH FEATURE Color green cyan magenta blue red Feature Odometry Disparity Vanishing Point 1 Vanishing Point 2 Corner x (m) (std. dev.) -5.0 (10.0) -9.5 (7.5) -9.0 (6.7) -7.8 (6.4) -4.7 (6.2) y (m) (std. dev.) -10.0 (10.0) -6.8 (5.6) -6.3 (4.3) -5.0 (3.7) -10.5 (3.6) 0 ( °) (std. dev.) 140.0 (10.0) 141.8 (7.5) 142.7 (4.7) 144.8(3.1) 148.8 (3.0) The table clearly demonstrates the improvements achieved by integrating several visual features using the proposed algorithm. CONCLUSION AND FUTURE WORK In this paper, an approach to determine the robot pose was presented in an urban area where GPS can not work since the satellite signals are often blocked by buildings. We tested the method with real data and the obtained results show that the method is potentially applicable even in the presence of errors in feature detection of the visual features and incomplete model description of the rough map. This method is a part of an ongoing research aiming autonomous outdoor navigation of a mobile robot. The system depends on the stereo vision and the rough map to compensate for the long-term unreliability of the robot odometry. No environmental modifications are needed. Future works include performing experiments at other various places in our campus to test the robustness of the proposed approach in more detail. And finally, we will apply the approach described in this research to the autonomous navigation of a mobile robot in an outdoor urban, man-made environment consisting of polyhedral buildings. REFERENCES Chronis G. and Skubic M. (2003). Sketch-Based Navigation for Mobile Robots. Proc. of IEEE Int. Conf. on Fuzzy Systems 284-289. DeSouza G.N. and Kak A.C. (2002). Vision for Mobile Robot Navigation: A Survey. IEEE Trans, on Pattern Analysis and Machine Intelligence 24:2, 237-267. Georgiev A. and Allen P.K. (2002). Vision for Mobile Robot Localization in Urban Environments. Proc. of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems 472-477'. Katsura H. Miura J. Hild M. and Shirai Y. (2003). A View-Based Outdoor Navigation using Object Recognition Robust to Changes of Weather and Seasons. Proc. of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems 2974-2979. Moon I. Miura J. and Shirai Y. (2002). On-line Extraction of Stable Visual Landmarks for a Mobile Robot with Stereo Vision. Advanced Robotics 16:8, 701-719. Tomono M. and Yuta S. (2001). Mobile Robot Localization based on an Inaccurate Map. Proc. of IEEE/RSJ Int. Conf on Intelligent Robots and Systems 399-405. 229 Ch47-I044963.fm Page 229 Thursday, July 27, 2006 7:59 AM Ch47-I044963.fm Page 229 Thursday, July 27, 2006 7:59 AM 229 TEACHING A MOBILE ROBOT TO TAKE ELEVATORS Koji Iwase, Jun Miura, and Yoshiaki Shirai Department of Mechanical Engineering, Osaka University Suita, Osaka 565-0871, Japan ABSTRACT The ability of moving between floors by using elevators is indispensable for mobile robots operating in office environments to expand their work areas. This paper describes a method of interactively teach- ing the task of taking elevators for making it easier for the user to use such robots for various elevators. The necessary knowledge of the task is organized as the task model. The robot examines the task model and determines what are missing in the model, and then asks the user to teach them. This enables the user to teach the necessary knowledge easily and efficiently. Experimental results show the potential usefulness of our approach. KEYWORDS Mobile robots, Interactive teaching, Task models, Take an elevator, Visual navigation. INTRODUCTION The ability of moving between floors by using elevators is indispensable for mobile robots perform- ing service tasks in office environments to extend their working areas. We have developed a mobile robot that can take elevators, but we had to give the robot in advance the necessary knowledge such as the shape of the elevator and the positions of the buttons. Since the necessary knowledge of the task of taking elevators is different from place to place, it is desirable that the user can easily teach such knowledge on-site. We have been developing a teaching framework called task model-based interactive teaching (Miura et al. 2004), in which the robot examines the description of a task, called task model, to determine miss- ing pieces of necessary knowledge, and actively asks the user to teach them. We apply this framework to the task of taking elevators (take-an-elevator task) by our robot (see Fig. 1). This paper describes the task models and the interactive teaching method with several teaching examples. TASK MODEL-BASED INTERACTIVE TEACHING Interaction between the user and a robot is useful for an efficient and easy teaching of task knowledge. Without interaction, the user has to think by himself/herself about what to teach to the robot. This is difficult for the user partly because he/she does not have enough knowledge of the robot's ability (i.e., what the robot can (or cannot) do), and partly because the user's knowledge may not be well-structured. If the robot knows of what are needed for achieving the task, then the robot can ask the user to teach them; this enables the user to easily give necessary knowledge to the robot. This section explains the representations for task models and the teaching strategy. 230 omnidirectional stereo laser range finder manipulator with a camera host computer move to elevator hall move to position P take elevator to floor F push button move to button go to position P at floor F move to button push button move to wait position move and push button get on elevator Ch47-I044963.fm Page 230 Thursday, July 27, 2006 7:59 AM Ch47-I044963.fm Page 230 Thursday, July 27, 2006 7:59 AM 230 omnidirectional stereo host computer Figure 1: Our mobile robot. go to position P at floor F move to elevator hall —*j take elevator to floor F \—»J move to position P ve and push button r~+\ move to wait position r-+\ get on elevator r-** •• Figure 2: A hierarchical structure of the take-an- elevator task. move to button Detect and localize the button by LRF and omni-camcra i button position —H Plan trajectory —4 Follow trajectory using LRF 1 s (a) move to button. Figure 3: Diagrams for example primitives Task Model push button r Detect and local the button bv template-matchir template image . Dashed lines S —+\ Move, manipulator]—• Recogn ize pushing of the button (b) push the button, indicate dependencies. No In our interactive teaching framework, the knowledge of a task is organized in a task model, in which necessary pieces of knowledge and their relationships are described. Some pieces of knowledge require other ones; for example, a procedure for detecting an object may need the shape or the color of the object. Such dependencies are represented by the network of knowledge pieces. The robot examines what are given and what are missing in the task model, and asks the user to teach the missing pieces of knowledge. Hierarchical Task Structure Robotic tasks usually have hierarchical structures. Fig. 2 shows a hierar- chy of robot motions for the take-an-elevator task. For example, a subtask, move and push button, is further decomposed into two steps (see the bottom of the figure): moving to the position where the robot can push the button, and actually pushing the button by the manipulator using visual feedback. Such a hierarchical task structure is the most basic representation in the task model. Non-terminal nodes in a hierarchical task structure are macros, which are further decomposed into more specific subtasks. Terminal nodes are primitives, the achievement of which requires actual robot motion and sensing operations. Robot and Object Models The robot model describes knowledge of the robot system such as the size and the mechanism of components (e.g., a mobile base and an arm) and the function and the position of sensors (e.g., cameras and range finders). Object models describe object properties including geometric ones, such as size, shape, and pose, and photometri c ones related to visual recognition. Movements The robot has two types of movements: free movement and guarded movement. A free movement is the one that the robot is required to a given destination without colliding with obstacles; the robot does not need to follow a specific trajectory. On the other hand, in a guarded movement, the robot 231 Ch47-I044963.fm Page 231 Thursday, July 27, 2006 7:59 AM Ch47-I044963.fm Page 231 Thursday, July 27, 2006 7:59 AM 231 has to follow some trajectory, which is usually generated from the configuration of surrounding obstacles; movements of this type are basically used for reaching a specific pose (position and orientation) or for passing through a narrow space. Fig. 3(a) shows the diagram for the subtask of moving to the position where the robot can push a button. Hand Motions Hand motions are described by its trajectory. They are usually implemented as sensor- feedback motions. Fig. 3(b) shows the diagram for the subtask of pushing a button. Sensing Skills A sensing operation is represented by a sensing skill. Sensing skills are used in vari- ous situations such as detecting and recognizing objects, measuring properties of objects, and verifying conditions on the geometric relationship between the robot and the objects. Interactive Teaching Using Task Model The robot tries to perform a task in the same way even in the case where some pieces of knowledge are missing. When the robot cannot execute a motion because of a missing piece of knowledge, the robot pauses and generates a query to the user for obtaining it. By repeating this process, the robot completes the task model with leading the interaction with the user. It could be possible to examine the whole task model before execution and to generate a set of queries for missing pieces of knowledge. ANALYSIS OF TAKE-AN-ELEVATOR TASK The take-an-elevator task is decomposed into the following steps: (1) Move to the elevator hall from the current position. This step can be achieved by the free space recognition and the motion planning ability of the robot (Negishi, Miura, and Shirai 2004), pro- vided that the route to the elevator hall is given. (2) Move to the place in front of the button outside the elevator, where the manipulator can reach the button. The robot recognizes the elevator and localizes itself with respect to the elevator's local coordinates. For the movement, the robot sets a trajectory from the current position to the target position, and follows it by a sensory-feedback control. (3) Localize the button and push it using the manipulator. The robot detects that the button is pushed by recognizing that the light of the button turns on. (4) Move to the position in front of the elevator door where the robot waits for the door to open. (5) Get on the elevator after recognizing the door's opening. (6) Localize and push the button of the destination floor inside the elevator, as the same as (3). (7) Get off the elevator after recognizing that the door opens (currently, the arrival at the target floor is not verified using floor signs inside the elevator). (8) Move to the destination position at the target destination floor, as the same as (1). Based on this analysis, we developed the task model for the take-an-elevator task. Fig. 4 shows that the robot can take an elevator autonomously by following the task model. TEACHING EXAMPLES The robot examines the task model, and if there are missing pieces of knowledge in it, the robot acquires them through the interaction with the user. Each missing piece of knowledge needs the corre- sponding teaching procedure. The above steps of the take-an-elevator task are divided into the following two parts. Steps (1) and (8) are composed of free movements. The other steps are composed of guarded movements near the elevator and hand motions. The following two subsections explain the teaching methods for the first and the second parts, respectively. 232 Ch47-I044963.fm Page 232 Thursday, July 27, 2006 7:59 AM Ch47-I044963.fm Page 232 Thursday, July 27, 2006 7:59 AM 232 approach an elevator push the button wait for the opening get on the elevator push the button inside get off the elevator Figure 4: The mobile robot is taking an elevator. Route Teaching The robot needs a free space map and a destination or a route to perform a free movement. The free space map is generated by the map generation capability of the robot, which is already embedded (Miura, Negishi, and Shirai 2002). The destination may be given by some coordinate values, but they are not intuitive for the user to teach. So we take the following "teaching by guiding" approach (Katsura et al. 2003, Kidono, Miura, and Shirai 2002). In route teaching, we first take the robot to a destination. During this guided movement, the robot learns the route. Then the robot can reach the destination by localizing itself with respect to the learned route. Such two-phase methods have been developed for both indoor and outdoor mobile robots; some of them are map-based (Kidono, Miura, and Shirai 2002, Maeyama, Oya, and Yuta 1997) and some are view-based (Katsura et al. 2003, Matsumoto, Inaba, and Inoue 1996). In this work, the robot simply memorizes the trace of its guided movement. Although the estimated trace suffers from accumulated errors, the robot can safely follow the learned route because of the reliable map generation; the robot moves to the direction of the destination within the recognized free space. The next problem is how to guide the robot. In Katsura et al. (2003) and Kidono, Miura, and Shirai (2002), we used a joystick to control the robot; but this requires the user to know the mechanism of the robot. A user-friendly way is to implement a person-following function to the robot (Huber and Kortenkamp 1995, Sawano, Miura, and Shirai 2000). For a simple and reliable person detection, we use a teaching device which has red LEDs; the user shows the device to the robot while he/she guides it to the destination (see Fig. 5). The robot repeatedly detects the device in both of the two omnidirectional camera by using a simple color-based detection algorithm, and calculates its relative position in the robot coordinates. The calculated position is input to our path planning method (Negishi, Miura, and Shirai 2004) as a temporary destination. Fig. 6 shows a snapshot of person tracking during a guided movement. Teaching of Vision-Based Operation This section describes the methods for teaching the position of an elevator, the positions of buttons, and the views of them. Teaching the Elevator Position Suppose that the robot has already be taken to the elevator hall, using the method described above. The robot then asks about the position of the elevator. The user indicates it by pointing the door of the elevator (see Fig. 7). The robot has a general model of elevator shape, which is mainly composed of two parallel lines corresponding to the wall and the elevator door projected onto the floor. Using this model and the LRF (laser range finder) data, the robot searches the indicated area for the elevator and sets the origin of the elevator local coordinates at the center of the gap of the wall in front of the door (see Fig. 8). 233 Ch47-I044963.fm Page 233 Thursday, July 27, 2006 7:59 AM Ch47-I044963.fm Page 233 Thursday, July 27, 2006 7:59 AM 233 Figure 5: Taking the robot to the destination. track of the user track of the robot Figure 6: Tracking the user. The white area is the detected free space. elevator door wall robot position Figure 7: Teaching the elevator position to the robot. Figure 8: Elevator detection from the LRF data. Figure 9: A detected but- ton outside the elevator. Teaching the Button Position The robot then asks where the buttons are, and the user indicates their rough position. The robot searches the indicated area on the wall for image patterns which match the given button models (e.g., circular or rectangular). Fig. 9 shows an example of detected button. The position of the button with respect to the elevator coordinates and the button view, which is used as an image template, are recorded after the verification by the user. The robot learns the buttons inside the elevator in a similar way; the user indicates the position of the button box, and the robot searches there for buttons. CONCLUSION This paper has described a method of interactively teaching the task of taking elevators to a mobile robot. The method uses task models for describing the necessary pieces of knowledge for each task and their dependencies. Task models include the following three kinds of robot-specific knowledge: object models, motion models, and sensing skills. Using the task model, the robot can determine what pieces of knowledge are further needed, and plans necessary interactions with users to obtaining them. By this method, the user can teach only the important pieces of task knowledge easily and efficiently. We have shown the preliminary implementation and experimental results on the take-an-elevator task. Currently the task model is manually designed for the specific, take-an-elevator task from scratch. It would be desirable, however, that a part of existing task models can be reused for describing another. Since reusable parts are in general commonly-used, typical operations, a future work is to develop a repertoire of typical operations by, for example, using an inductive learning-based approach (Dufay and Latombe 1984, Tsuda, Ogata, and Nanjo 1998). By using the repertoire, the user's effort for task modeling is expected to be reduced drastically. Another issue is the development of teaching procedures. Although the mechanism of determining missing pieces of knowledge in a dependency network is general, for each missing piece, the corre- sponding procedure for obtaining it from the user should be provided. Such teaching procedures are also designed manually at present and, therefore, the kinds of pieces of knowledge that can be taught [...]... and Pope S T ( 198 8) For Using the Model-view-controller User Interface Paradigm in Smalltalk-80 Journal of Object-Oriented Programing 1:3, 2 6-4 9 Shimomura Y and Tomiyama T (2002) Service Modeling for Service Engineering Proceedings of The 5th International Conference on Design of Information Infrastructure Systems for Manufacturing 2002,30 9- 3 16 Shimomura Y., Watanabe K., Arai T., Sakao T and Tomiyama... References McCallum, A ( 199 6) Learning to Use Selective Attention and Short-Term Memory in Sequential Tasks Proceedings of International Conference on Simulation of Adaptive Behavior, 31 5-3 24 Minato, T and Asada, M (2003) Towards Selective Attention: Generating Image Features by Learning a Visuo-Motor Map Robotics and Autonomous Systems 45, 21 1-2 21 Mitsunaga, N and Asada, M (2000) Observation Strategy for Decision... 40: 2-3 , 12 1-1 30 S Maeyama, A Ohya, and S Yuta Autonomous Mobile Robot System for Long Distance Outdoor Navigation in University Campus J of Robotics and Mechatronics, Vol 9, No 5, pp 34 8-3 53, 199 7 Y Matsumoto, M Inaba, and H Inoue ( 199 6) Visual Navigation using View-Sequenced Route Representation In Proceedings of 199 6 IEEE Int Conf on Robotics and Automation, 8 3-8 8 J Miura, Y Negishi, and Y Shirai... on Machine Automation, 38 9- 3 94 M Tsuda, H Ogata, and Y Nanjo ( 199 8) Programming Groups of Local Models from Human Demonstration to Create a Model for Robotic Assmebly In Proceedings of 199 8 IEEE Int Conf on Robotics and Automation, 53 0-5 37 235 GENERATED IMAGE FEATURE BASED SELECTIVE ATTENTION MECHANISM BY VISUO-MOTOR LEARNING 1 Department of Adaptive Machine Systems, Graduate School of Engineering,... Paredis, and Khosla 2002) are suitable for this purpose Acknowledgments This research is supported in part by Grant -in- Aid for Scientific Research from Ministry of Eduction, Culture, Sports, Science and Technology, the Kayamori Foundation of Informational Science Advancement, Nagoya, Japan, and the Artificial Intelligence Research Promotion Foundation, Nagoya, Japan REFERENCES B Dufay and J.C Latombe ( 198 4)... Robots with a Fine Tool for Microscopic Operations Proc of 2004IEEE/RSJ International Conf on Intelligent Robots and Systems 21 3-2 23 [5] H Aoyama, F Iwata, and A Sasaki ( 199 5) Desktop flexible manufacturing system by movable micro robots Proc of Int Conf.on Robotics and Automation, 66 0-6 65 [6] F Arai, A Ichikawa, M Ogawa, T Fukuda, K Horio and K Itoigawa (2001) High Speed Separation System of Single Microbe... IDEA In the proposed method, a robot generates an image feature extractor that is necessary for the action selection through visuo-motor map learning (Minato & Asada, 2003) The state calculation process is decomposed into feature extraction and state extraction (Figure l (a) ) A robot learns the effective feature extractor and state mapping matrix for a given task through a mapping from observed images... Chiba Naoto 2, Takashi Usuda3, Ohmi Fuchiwaki 2 and Hisayuki Aoyama2 1 Department of Mechanical Engineering, Shizuoka Institute of Science and Technology, 220 0-2 , Toyosawa, Fukuroi, Shizuoka 43 7-8 555,.Tapan Department of Mechanical Engineering & Intelligent Systems, University of ElectroCommunications, Tokyo 1-5 -1 , Chofu, Tokyo 18 2-8 585 ,Japan 3 Advanced Industrial Science and Technology,Umezono 1-1 ,... boundary for recognition of front area is extracted Pre-processing of recognition of the object of circle shape assigns a label number to a continuous pixel area, after calculating the bit map image of a CCD camera The circular value (Value shows circle-likeness) is calculated to each labelling area A circular domain is extracted using this value and threshold value The circular value e is calculated by... ( 198 4) An Approach to Automatic Robot Programming Based on Inductive Learning Int J of Robotics Research, 3:4, 3-2 0 E Huber and D Kortenkamp ( 199 5) Using Stereo Vision to Pursue Moving Agents with a Mobile Robot In Proceedings of 199 5 IEEE Int Conf on Robotics and Automation, 234 0-2 346 S Iba, CJ Paredis, and P.K Khosla (2002) Interactive Multi-Modal Robot Programming In Proceedings of 2002 IEEE Int Conf . 2006 7: 59 AM 2 29 TEACHING A MOBILE ROBOT TO TAKE ELEVATORS Koji Iwase, Jun Miura, and Yoshiaki Shirai Department of Mechanical Engineering, Osaka University Suita, Osaka 56 5-0 871, Japan ABSTRACT The. developed for both indoor and outdoor mobile robots; some of them are map-based (Kidono, Miura, and Shirai 2002, Maeyama, Oya, and Yuta 199 7) and some are view-based (Katsura et al. 2003, Matsumoto,. Engineering, Osaka University, 2-1 Yamada-oka, Suita, Osaka 56 5-0 871 Japan ABSTRACT Visual attention is an essential mechanism of an intelligent robot. Existing research typically specifies in advance